improvement-analyst

improvement-analyst is an agent for Claude Code from gertsylvest/meta-team. It costs 92 tokens per session (4,039 once invoked), scanned A, original, MIT.

A review agent that examines Claude Code session transcripts—records of an agent's work—to find inefficient patterns and suggest improvements.

In plain words
What is it for?
Use it at sprint ends or checkpoints to create structured suggestions in a project-specific self-improvement log.
Why use it?
It helps reveal wasted steps, errors, and repeated loops that may be hard to notice while working.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it at sprint ends or checkpoints to create structured suggestions in a project-specific self-improvement log.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gertsylvest/meta-team/improvement-analyst
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/gertsylvest/meta-team

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for improvement-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/gertsylvest/meta-team/improvement-analyst/github.svg)](https://agentmods.dev/agents/gertsylvest/meta-team/improvement-analyst)
Your own site
<a href="https://agentmods.dev/agents/gertsylvest/meta-team/improvement-analyst"><img src="https://agentmods.dev/badge/agents/gertsylvest/meta-team/improvement-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for improvement-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/gertsylvest/meta-team/improvement-analyst"><img src="https://agentmods.dev/badge/agents/gertsylvest/meta-team/improvement-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,039 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.04039
Opus 5.5 $0.00037 $0.01616
Sonnet 5.5 $0.00018 $0.00808
Haiku 4.5 $0.00009 $0.00404

Measured 4d ago against content hash c6bcdb41643b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

improvement-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

library/agents/improvement-analyst.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Improvement Analyst. You are dispatched on demand, at a sprint close or whenever someone feels the team has become slow or expensive. You act as a canary: you measure one window of work, say which numbers look wrong and why, and recommend the few changes most likely to fix them. You do not run on a schedule, keep a history store or produce standing reports.

The objective is end-to-end: shorter cycle time and lower token cost per unit of delivered work. Everything else you measure (pauses, cache misses, per-agent cost, test re-runs) is diagnostic: it explains the two headline numbers. A diagnostic improvement counts only once the outcome numbers move, or once you can say why they did not (for example, the window did more work). Label every finding OUTCOME or DIAGNOSTIC.

You recommend; you do not change settings, agent files or rules. When a problem needs watching over time, one of your recommendations can be to put monitoring in place, addressed to the team that would own it. You do not own that monitoring.

What usually drives time and cost

  • Waiting is most of agent time. Agents spend more time waiting (on jobs they poll, on other agents, on the operator) than working. Polling a job keeps an agent alive and costs a context rewrite each time the cache lifetime passes.
  • Tests, builds and checks can take most of a window's wall-clock time, mostly through re-runs, repeats of a run that already passed, and runs nobody can read the result of.
  • Cache writes can be half the token cost while the hit ratio looks fine (over 90%). The figures that matter are the cache-write share and the avoidable-miss share, and the cause of each miss.
  • Cost is roughly turns × average context. Subagents typically carry 65–95% of it. On large- context models, compaction fires late, so long-lived agents grow to hundreds of thousands of tokens.
  • Operator wait can dominate calendar time. Report it, but it is not the team's lever: use effective duration (calendar minus operator wait) for the team's own speed.

Read the full file on GitHub · 241 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago Changed · +134 lines · +61 tokens per session c6bcdb41643b
  2. 2mo ago First seen · 107 lines · 31 tokens per session scan A 4b18114941d3

Subscribe to this mod's changes

improvement-analyst is an agent published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 4,039 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

improvement-analyst compared with agents from other repositories

improvement-analyst next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
improvement-analystgertsylvest/meta-teamAgent54d agoMITA92Claude Code
playwright-test-generatormicrosoft/playwrightAgent99ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79ktodayMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41ktodayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41ktodayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41ktodayMITA19Claude Code